There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Capturing high-quality ocean surface images plays an important role in lots of visual tasks about ocean such as marine oil spill tracking and Ulva (U.) prolifera detection. In the natural scene, sun shines the surface of ocean directly and causes specular reflection, the images of ocean surface captured by camera often have large number of specular highlight component which has great negative impact to visual tasks of ocean. Different from the samples adopted in current highlight removal method, the specular highlight component is distributed in whole ocean surface images. And in many pixels, the specular reflection component is much larger than the pure diffuse reflection and even goes beyond the dynamic range of brightness that image can store. So if just separating highlight component from the original image, many dark spots will remain in the original image and high quality images cannot be obtained. In this paper, we propose a specular reflection removal method for large-scale ocean surface images captured by UVA. The method proposed in this paper includes two parts: highlight detection and image inpainting in highlight regions. The method based on intensity ratio is used to extract the highlight regions in ocean surface images and then image inpainting method based on FMM can inpaint these regions in a relatively short time. Experimental results show that our method can effectively remove the highlight component and get higher quality images of ocean surface.

A Specular Reflection Removal Method for Large Scale Ocean Surface Images

This study looks into the stumbling block of temporal activity localization via natural language (TALL) in the untrimmed video. It’s a difficult task since the target temporal activity may be misled by disorder query. Existing approaches used sliding windows, regression, and ranking to handle the query without the usage of grammar-based rules. When a query is out of sequence and cannot be correlated with the relevant activity, these approaches suffer performance deterioration. We introduce the visual, action, object, and connecting words concepts to address the issue of non-sequence queries. Integration of visual-textual entities network (IVTEN) is our proposed architecture, which consists of three submodules: (1) visual graph convolutional network (visual-GCN), (2) textual graph convolutional network (textual-GCN), and (3) compatible method for learning embeddings (CME). Visual nodes detect activity, object, and actor in the same way as textual nodes maintain word sequence using grammar-based rules. (CME) integrates several modalities (activity, query) and trained grammar-based words into the same embedding space. We also include a stochastic latent variable in CME to align and retain the query sequence with the relevant activity. On three typical benchmark datasets, our IVTEN approach outperforms the state-of-the-art Charades-STA, TACoS, and ActivityNet-Captions.

IVTEN: integration of visual-textual entities for temporal activity localization via language in video

In recent years, ocean front tracking is of vital importance in ocean-related research, and many algorithms have been proposed to identify ocean fronts. However, all these methods focus on single frame ocean-front classification instead of ocean-front tracking. In this paper, we propose an ocean-front tracking dataset (OFTraD) and apply GoogLeNet inception network to track ocean fronts in video sequences. Firstly, the video sequence is split into image blocks, then the image blocks are classified into ocean-front and background by GoogLeNet inception network. Finally, the labeled image blocks are used to reconstruct the video sequence. Experiments show that our algorithm can achieve accurate tracking results.

Application of GoogLeNet for ocean-front tracking

Linear spectral unmixing is an important technique in the analysis of mixed pixels in hyperspectral images. In recent years, deep learning-based methods have been garnering increasing attention in hyperspectral unmixing; especially, unsupervised autoencoder (AE) networks that have achieved excellent unmixing performance are a recent trend. While most approaches use spatial information, it is well known that hyperspectral data are characterized by a large number of narrow spectral bands. In order to take full advantage of the hyperspectral bands in unmixing and the spatial information, in this article, we explore multiview spectral and spatial information in an AE-based unmixing framework. We introduce multiview spectral information through spectral partitioning and propose a multiview spatial–spectral two-stream network, called MSSS-Net, which simultaneously learns a spatial stream network and a multiview spectral stream network in an end-to-end fashion for more efficient unmixing. The MSSS-Net is a two-stream deep unmixing network sharing a decoder, where its two AE networks employ recurrent neural networks (RNNs) to collaboratively utilize multiview spectral and spatial information. The spatial stream network branch extracts the spatial features of pixels and its neighbors, while the multiview spectral stream network branch exploits the multiview spectral bands of a pixel. Meanwhile, we design a cascaded bidirectional and unidirectional RNNs’ encoder structure for multiview spatial–spectral information to learn more discriminative deep patch-pixel features. Extensive ablation studies and experiments on both synthetic and real datasets demonstrate the superiority of the MSSS-Net over state-of-the-art unmixing methods.

Multiview Spatial–Spectral Two-Stream Network for Hyperspectral Image Unmixing

We extend previous work regarding the transitivity of fuzzy matrices and propose the concept of completely transitive matrices. We further investigate their properties, indices, periods and relations with canonical fuzzy matrices. Our research shows that the completely transitive matrix type is a novel type, which contains previously defined transitive matrix types. Based on the proposed theories, we illustrate that completely transitive matrices can be applied in fuzzy orderings.

Junyu Dong

Papers

A Specular Reflection Removal Method for Large Scale Ocean Surface Images

IVTEN: integration of visual-textual entities for temporal activity localization via language in video

Application of GoogLeNet for ocean-front tracking

Multiview Spatial–Spectral Two-Stream Network for Hyperspectral Image Unmixing

Fuzzy matrices with complete transitivity